"speculative decoding" Jobs

30 open tech roles matching “speculative decoding”, taken straight from company career pages — not reposted from other job boards. Most in demand right now: Python, CUDA, C++. Every listing is re-checked daily and closed roles are removed.

Showing 20 of 30 results

Sarvam AI

Own Sarvam's production serving path for large distributed models, integrating and optimizing performance across a multi-node stack.

Sarvam AI Bengaluru Published 1 month ago
baseten

Join Baseten as a Software Engineer focused on ML performance to optimize large language models in a fast-paced startup environment.

baseten San Francisco Published 2 years ago
Flexible on stack
Hippocratic AI

Own the serving infrastructure for healthcare AI, optimizing LLM inference systems to enhance patient experiences.

Hippocratic AI Menlo Park, CA Published 2 weeks ago
Flexible on stack
Inworld AI

Join Inworld AI as a Staff/Principal Machine Learning Engineer to optimize and serve top-ranked realtime voice models.

Inworld AI UK £140k–£200k/yr Published 5 months ago
Flexible on stack
Inworld AI

Join Inworld AI as a Staff/Principal Machine Learning Engineer to optimize and serve top-ranked realtime voice models.

Inworld AI Mountain View, California, USA $270k–$500k/yr Published 5 months ago
Flexible on stack
Mirendil

Own the inference systems that power frontier AI models in production and research at a tech-first startup.

Mirendil San Francisco $300k–$400k/yr Published 2 months ago
Inworld AI

Join Inworld AI as a Staff/Principal Machine Learning Engineer to optimize and serve state-of-the-art voice models in a fully remote role.

Inworld AI Switzerland Published 5 months ago
Flexible on stack
Inworld AI

Join Inworld AI as a Lead Machine Learning Engineer to optimize and serve state-of-the-art voice models in a dynamic startup environment.

Inworld AI Germany Published 5 months ago
Flexible on stack
Inworld AI

Join Inworld AI as a Lead Machine Learning Engineer to optimize and serve state-of-the-art voice models in a dynamic environment.

Inworld AI Serbia Published 5 months ago
Flexible on stack
Inferact

Join Inferact as a Developer Relations Engineer to shape how developers learn and build with vLLM, the AI inference engine.

Inferact San Francisco $200k–$400k/yr Published 2 months ago
Flexible on stack
SpaceX

Join SpaceX as a Software Engineer to develop high-performance AI inference systems for mission-critical applications.

SpaceX Palo Alto, CA $135k–$175k/yr Published 3 weeks ago
Flexible on stack
Together AI

Join Together AI as a Forward Deployed Engineer to optimize inference systems for strategic customers in a hands-on role.

Together AI Singapore Published 1 month ago
Flexible on stack 70% coding
Perplexity AI

Join Perplexity AI as an AI Inference Engineer to optimize and develop our inference engine for various model architectures.

Perplexity AI London Published 5 months ago
Flexible on stack
DeepL

Lead the Production Inference team at DeepL, focusing on performance-critical model serving systems in a fast-paced AI environment.

DeepL London Published 1 month ago
Heavy meetings
Perplexity AI

Join Perplexity AI as a Technical Staff member to enhance our AI inference engine with cutting-edge technologies.

Perplexity AI San Francisco Published 5 months ago
Flexible on stack
baseten

Join Baseten as a Software Engineer focusing on Model APIs to enhance AI model performance and developer experience.

baseten San Francisco Published 11 months ago